Trajectory-based Learning for Ball-in-Maze Games
This is an incremental improvement for robotics and game AI applications.
The paper tackles the problem of sample inefficiency in deep reinforcement learning for Ball-in-Maze Games by using simulator-generated trajectories, resulting in a 2-3x speed-up in learning.
Deep Reinforcement Learning has shown tremendous success in solving several games and tasks in robotics. However, unlike humans, it generally requires a lot of training instances. Trajectories imitating to solve the task at hand can help to increase sample-efficiency of deep RL methods. In this paper, we present a simple approach to use such trajectories, applied to the challenging Ball-in-Maze Games, recently introduced in the literature. We show that in spite of not using human-generated trajectories and just using the simulator as a model to generate a limited number of trajectories, we can get a speed-up of about 2-3x in the learning process. We also discuss some challenges we observed while using trajectory-based learning for very sparse reward functions.